© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 10917
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to programming code, particularly focusing on the organization of data and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.76
    хьтан
    -0.73
     transfieras
    -0.70
    ंदीखरीदारी
    -0.68
    تقاوى
    -0.66
     AssemblyCulture
    -0.66
     समीक्षाओं
    -0.65
     MainAxisSize
    -0.65
    complexContent
    -0.65
     ویکی‌پدی
    -0.65
    POSITIVE LOGITS
     '
    0.47
    CURLOPT
    0.47
     ‘
    0.44
     CURLOPT
    0.43
    '
    0.35
     «
    0.35
     mercenaries
    0.33
     المؤ
    0.33
    '_
    0.32
     mercen
    0.32
    Activations Density 0.361%

    No Known Activations